- dsh-novel-writer — 网文写作体检 @siweina/dsh-novel-writerOffline toolkit: 19 tools for Chinese web-novel style, plot-thread and continuity audits.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.22 GitHub stars.
- Promptheus @abhichandra21/promptheusAI-powered prompt refinement with adaptive questioning and multi-provider support (6+ LLM backends)4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.17 GitHub stars.
- dyslex.ia @firou91/dyslex-iaAccessibility MCP server and Agent Skills for AI agents. Requires Superpowers.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.7 GitHub stars.
- slop-chop @dcadolph/slop-chopFind and remove the writing patterns a profile lists. Deterministic rules, model rewrite opt-in.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.4 GitHub stars.
- Obelisk @zachhannum/obeliskComment on a passage of an Obsidian note, and propose suggested edits.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- PublishReady @veldica/publishreadyPublishReady: Deterministic writing control with local-first metrics and AI prose audits.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Lectura Facil Lint Es @jmshinhwa/lectura-facil-lint-es12 reglas de lectura fácil para guías y formularios de trámite (RD 707/2026, UNE 153101)4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- GoHumanize Open Humanizer @gohumanize-ai/gohumanize-open-humanizer-mcpRewrite AI-styled text into natural writing with a fine-tune model.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- NewsBlog Composer @mohammed-jameal-j/newsblog-composerVerifies news stories, mines SEO keywords, builds schema and reviews your draft. You write it.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Ryter Pro @apiihub33-cyber/ryterpro-mcpMCP server for humanizing and rewriting text with the Ryter Pro API.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Promptlint MCP @sean-sunagaku/promptlint-mcpStatic linter for AI prompts: contradictions, redundancy, ambiguity, and fluff.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Writing MCP @hannasdev/mcp-writingMetadata-first fiction editing and reasoning tools for long-form writing projects.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Alchemy @fernforge/alchemyServes the Alchemy writing ruleset to any agent, so its prose loses the usual LLM tells.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- defluff @ahmedak/defluffDeterministic prose linter for LLM text — flags AI slop, filler, buzzwords, hedges, clichés.2% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- PersonaMCP @robyroro/personamcpLocal-first memory of how you write: style profile and real reply examples from your chat exportsNot assessed yet.Runs on your machine, installed from PyPI.
- Lexilint @raunakkathuria/lexilintOffline spell checker + BYOK grammar for AI assistants. Works with Claude Desktop, ChatGPT, Cursor.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- LanguageTool @mrfentmen/languagetool-mcpKeyless MCP server for LanguageTool: grammar, spelling and style checking in 30+ languages.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- HumanifyMe @joshmcq/humanifymeLearns your writing voice locally and rewrites AI drafts so they sound like you.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Stylemcp @3dunlmtd/stylemcpBrand rules for AI outputs. Validate and rewrite text to match your brand voice.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Ticket AI @syrian963/ticket-ai-mcpMeasures tickets against the ones your team already shipped: sections, length, labels, duplicates.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Unswell @stokaro/unswellOffline self-checking to reduce AI-style wording in source code and documentation.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.
Writing assistance MCP servers
A server here drafts, edits or proofreads text: grammar, style, tone.
Not here: translation and fiction writing.
198 remote107 localTagged by Odel's AI, which can make mistakes
Most popular in Writing assistance
By GitHub stars, at most two per publisher- Number 1: humanizer-ru@ilyautov/humanizer-ruСледы нейросети в русском тексте: балл чистоты 0-100, запреты и маркеры с позициями, факт-замок.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.418 GitHub stars.
- Number 2: Scrivener@writerslogic/scrivener-mcpMCP server for Scrivener: read, write, analyze, and search your manuscripts with AI assistants.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.66 GitHub stars.
- Number 3: Signs of AI Writing@peopleworks/signs-of-aiAI-writing detection (EN/ES) that shows the evidence: named tells, hidden characters, citations.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from NuGet.27 GitHub stars.
